> ## Documentation Index > Fetch the complete documentation index at: https://docs.kataven.ai/llms.txt > Use this file to discover all available pages before exploring further. # Kataven MCP server — manage voice AI agents from any AI app, no code > Install one piece of software and let Claude, ChatGPT, Cursor, Windsurf, Zed, VS Code, JetBrains, Warp, Goose, n8n, or Raycast run your Kataven account by chat. No API calls, no scripts. **You don't need to write code.** The Kataven MCP server is a small program you install once on your laptop. After that, your favorite AI app — Claude Desktop, ChatGPT, Cursor, Windsurf, Zed, VS Code's Copilot, JetBrains, Warp, Goose, n8n, Raycast — can manage your Kataven voice agents *by chatting*. Ask Claude *"create a sales agent and place a test call to my cell"* and it does. No SDK, no curl, no Python. ## Who this page is for | You are… | Use this page if… | | ------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------- | | **A non-developer founder, ops lead, or marketer** running Kataven | You want to ask Claude / ChatGPT to do things ("pause the running campaign", "show me numbers without an agent") instead of clicking around the dashboard | | **An ops engineer** automating Kataven from a chat surface | You want one config blob you can paste into every team member's AI app | | **A solo developer using Claude Desktop, Cursor, or Zed** | You'd rather chat than install Python and write SDK calls | If you're using **Claude Code** or **Codex CLI** (terminal coding agents that have a shell), you don't need MCP — those tools install the [Python SDK](/sdks/python/overview) directly. See [Manage with Claude Code](/guides/manage-with-claude-code) or [Manage with Codex](/guides/manage-with-codex). MCP is for everything else. ## Two ways MCP clients connect `kataven-mcp` runs **locally on your machine over stdio** (a local pipe). Most AI apps connect to it directly. A few — ChatGPT, Claude.ai web, n8n — only accept **remote MCP URLs over HTTPS**, so you need a one-line tunnel to expose your local server publicly. | AI app | Connection | Difficulty | Guide | | ------------------------------------ | ----------------- | -------------------------------------- | ------------------------------------------- | | **Claude Desktop** | Direct stdio | 🟢 paste JSON, restart | [Setup →](/sdks/mcp/clients/claude-desktop) | | **Cursor** | Direct stdio | 🟢 paste JSON, restart | [Setup →](/sdks/mcp/clients/cursor) | | **Windsurf** | Direct stdio | 🟢 UI button + JSON | [Setup →](/sdks/mcp/clients/windsurf) | | **Zed** | Direct stdio | 🟢 settings.json edit | [Setup →](/sdks/mcp/clients/zed) | | **VS Code** (Copilot agent) | Direct stdio | 🟢 Command Palette | [Setup →](/sdks/mcp/clients/vs-code) | | **JetBrains AI Assistant** | Direct stdio | 🟢 UI form | [Setup →](/sdks/mcp/clients/jetbrains) | | **Warp Terminal** | Direct stdio | 🟢 UI button | [Setup →](/sdks/mcp/clients/warp) | | **Goose** | Direct stdio | 🟢 `goose configure` | [Setup →](/sdks/mcp/clients/goose) | | **Raycast AI** | Direct stdio | 🟢 install MCP extension | [Setup →](/sdks/mcp/clients/raycast) | | **ChatGPT** (Desktop + web + mobile) | Remote HTTPS only | 🟡 needs [tunnel](/sdks/mcp/tunneling) | [Setup →](/sdks/mcp/clients/chatgpt) | | **Claude.ai** web (Pro+) | Remote HTTPS only | 🟡 needs [tunnel](/sdks/mcp/tunneling) | [Setup →](/sdks/mcp/clients/claude-web) | | **n8n** | Remote SSE only | 🟡 needs [tunnel](/sdks/mcp/tunneling) | [Setup →](/sdks/mcp/clients/n8n) | Building your own AI agent (LangGraph, Agno, AutoGen, OpenAI Agents SDK)? Stdio works directly — see [Programmatic](/sdks/mcp/programmatic). ## The universal pattern Every client follows the same three steps: ```bash theme={null} pip install kataven-mcp ``` Don't have Python? On macOS run `brew install python` first; on Windows install [official Python 3.10+](https://www.python.org/downloads/). Full walkthrough: [Install →](/sdks/mcp/install). [hub.kataven.ai/settings](https://hub.kataven.ai/settings) → **API Keys** tab → **Create API key**. Copy the `sk_live_…` value once. Pick your client from the table above. Each guide is one page; the JSON entry is identical everywhere — only the file path or UI button differs. After step 3, restart the AI app and ask it to do something Kataven-related. The Kataven tools (`kataven_list_agents`, `kataven_create_agent`, `kataven_originate_call`, ...) appear in its tool picker. ## What the AI can do Real prompts that work once `kataven-mcp` is wired up: > "Show me every agent and which phone number it's pinned to. Anything pointing nowhere?" > "Create a 'Tier 2 Support' agent with a friendlier tone than the existing 'Support' agent. Attach the `general-faqs` playbook." > "Place a test call from +12025550123 to my cell +14155550100 using the Front Desk agent. Show me the live transcript link." > "Pause every running campaign — we're deploying a fix." Full list of exposed tools: see [Install § What gets exposed](/sdks/mcp/install#what-gets-exposed). ## Important reading before you go further * **[Tunneling](/sdks/mcp/tunneling)** — required if you're using ChatGPT, Claude.ai web, or n8n. * **[Security](/sdks/mcp/security)** — your `sk_live_` is full account scope; treat it like a CI deploy key. * **[Troubleshooting](/sdks/mcp/troubleshooting)** — what to do when tools don't appear. * **[Programmatic](/sdks/mcp/programmatic)** — OpenAI Agents SDK, LangGraph, Agno, AutoGen. ## Other ways to manage Kataven from AI * [Manage with Claude Code](/guides/manage-with-claude-code) / [Manage with Codex](/guides/manage-with-codex) — terminal coding agents (no MCP needed; they use the SDK directly). * [Manage with AI overview](/guides/ai-agents) — full decision matrix across every AI tool.